SBMSplitMerge1.1.1 package

Inference for a Generalised SBM with a Split Merge Sampler

accept

accept propsbm with the acceptance probability alpha

addblock

Add a block move

ARI

Adjusted Rand Index

blockmat.blocks

Block matrix

blockmat.numeric

Block matrix

blockmat

Block matrix

blockmat.sbm

Block matrix

blockmod

Block Model

blocks

Blocks object

blocktrace

plot a trace of the blocks from MCMC samples

crp

Chinese Restaurant Process

ddirichlet

Dirichlet distribution

dedges.numeric

likelihood of edges

dedges

Density of edges

dedges.sbm

Density of edges

delblock

Delete a block move

dma

Dirichlet Multinomial Allocation

drawblock.dp

Draw block membership

drawblock.gibbs

Gibbs-like reassignment of nodes to the current set of blocks

drawblocks.dp

Draw block memberships

drawblocks.gibbs

Gibbs-like reassignment of nodes to the current set of blocks

drawparams

Metropolis updates by drawing parameters

edgemod

Class for edge models

edges

Class for edge data

edges_bern

Bernoulli edge model

edges_nbin

Negative-Binomial edge model

edges_norm

Normal edge model

edges_pois

Poisson edge model

eval_plots

get a set of evaluation plots from MCMC samples

is.sbm

is.sbm

marglike_bern

Marginal likelihood model for Bernoulli distributed edges

marglike_norm

Marginal likelihood model for Normal distributed edges

marglike_pois

Marginal likelihood model for Poisson distributed edges

mergeavg

Merge blocks

mergeblocks

merge move block merging

mergeparams.default

Merge step: parameters

mergeparams.numeric

Merge step - parameter merging

mergeparams

merge parameters

modeblocks

modal block assignments from MCMC samples

multinom

Multinomial block assignment

nodelike

Likelihood of node assignment

numblockstrace

plot a trace of the number of blocks from MCMC samples

param_beta

Beta parameter model

param_gamma

Gamma parameter model

param_nbin

Parameter model for Negative Binomial

param_norm

Parameter model for Normal Model

parammat.blocks

Parameter Matrix

parammat.matrix

Parameter Matrix

parammat.params

Parameter Matrix

parammat

Parameter Matrix

parammat.sbm

Parameter Matrix

parammod

Parameter Model

params

params S3 object

paramtrace

plot a trace of parameter values from MCMC samples

plot.blocks

Plot blocks

plot.edges

Plot

plot.sbm

Plot for sbm object

plotpostpairs

helper function for trace plots

postpairs

mean proportion of times two nodes were in the same block under MCMC s...

rcat

Draw draw Categorical distribution

rdirichlet

Dirichlet distribution

redges

Simulate edges

rw

Random Walk

sampler.conj

Conjugate model sampler

sampler.dp

Dirichlet process sampler

sampler.gibbs

Gibbs sampling for node assignments

sampler

top level sampler function

sampler.rj

reversible jump Markov chain Monte Carlo split-merge sampler

sbm

Class sbm

sbmmod

Stochastic block model object

splitavg

split move using average to merge parameters

splitblocks

split move: blocks

splitparams.numeric

split move: params

splitparams.params

split move: params

splitparams

split move: parameters

updateblock.blocks

Update the block assignment of a node

updateblock

Update the block assignment of a node

updateblock.sbm

Update the block assignment of a node

vmeasure

V-measure

Inference in a Bayesian framework for a generalised stochastic block model. The generalised stochastic block model (SBM) can capture group structure in network data without requiring conjugate priors on the edge-states. Two sampling methods are provided to perform inference on edge parameters and block structure: a split-merge Markov chain Monte Carlo algorithm and a Dirichlet process sampler. Green, Richardson (2001) <doi:10.1111/1467-9469.00242>; Neal (2000) <doi:10.1080/10618600.2000.10474879>; Ludkin (2019) <arXiv:1909.09421>.

  • Maintainer: Matthew Ludkin
  • License: MIT + file LICENSE
  • Last published: 2020-06-04